finetuned_models/FF++_c23_32frames/experiments_test/README.md

Script of testing fine-tuned FSFM-3C model (ViT) for evaluation of cross-dataset deepfakes detection

CUDA_VISIBLE_DEVICES=0 OMP_NUM_THREADS=1 python -m torch.distributed.launch --nproc_per_node=1 main_test_DfD.py \
    --eval \
    --model vit_base_patch16 \
    --nb_classes 2 \
    --batch_size 320 \
    --resume ./checkpoint/finetuned_models/FF++_c23_32frames/checkpoint-min_val_loss.pth \
    --output_dir ./checkpoint/finetuned_models/FF++_c23_32frames/experiments_test/